{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TI7PGOHMNSC25UJM3ECX4WP3SV","short_pith_number":"pith:TI7PGOHM","schema_version":"1.0","canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","source":{"kind":"arxiv","id":"2001.05270","version":1},"attestation_state":"computed","paper":{"title":"Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marco A. Wiering, Mario S. Holubar","submitted_at":"2020-01-15T12:30:57Z","abstract_excerpt":"In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a randomly generated racetrack. Different versions of two actor-critic learning algorithms are tested on this environment: Sampled Policy Gradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG is introduced that aims to improve learning performance by weighting action samples during the policy update step. The effect of using experience replay"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2001.05270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T12:30:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c9ab067bff038be3b294027ed4ceacc70768874baafc1e4439754ba72577b354","abstract_canon_sha256":"44b4451ccfa07a31ce9f515ee1874ce8f14b347a59af7f112c48b00af4483840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:40.679365Z","signature_b64":"dminlrDwb4HCDIuy7S3/W6Zp/8/OhpLaey9a0oCWeQ+AbvtQ5usrWVzRyx71GZQZ50GU8aov4hTT0AkzMRdGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","last_reissued_at":"2026-07-05T00:33:40.678790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:40.678790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marco A. Wiering, Mario S. Holubar","submitted_at":"2020-01-15T12:30:57Z","abstract_excerpt":"In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a randomly generated racetrack. Different versions of two actor-critic learning algorithms are tested on this environment: Sampled Policy Gradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG is introduced that aims to improve learning performance by weighting action samples during the policy update step. The effect of using experience replay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05270","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.05270/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2001.05270","created_at":"2026-07-05T00:33:40.678857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.05270v1","created_at":"2026-07-05T00:33:40.678857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05270","created_at":"2026-07-05T00:33:40.678857+00:00"},{"alias_kind":"pith_short_12","alias_value":"TI7PGOHMNSC2","created_at":"2026-07-05T00:33:40.678857+00:00"},{"alias_kind":"pith_short_16","alias_value":"TI7PGOHMNSC25UJM","created_at":"2026-07-05T00:33:40.678857+00:00"},{"alias_kind":"pith_short_8","alias_value":"TI7PGOHM","created_at":"2026-07-05T00:33:40.678857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.18892","citing_title":"Non-Abelian and Type-A Conformal Anomalies from Euler Descent","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06032","citing_title":"Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters","ref_index":256,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV","json":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV.json","graph_json":"https://pith.science/api/pith-number/TI7PGOHMNSC25UJM3ECX4WP3SV/graph.json","events_json":"https://pith.science/api/pith-number/TI7PGOHMNSC25UJM3ECX4WP3SV/events.json","paper":"https://pith.science/paper/TI7PGOHM"},"agent_actions":{"view_html":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV","download_json":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV.json","view_paper":"https://pith.science/paper/TI7PGOHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.05270&json=true","fetch_graph":"https://pith.science/api/pith-number/TI7PGOHMNSC25UJM3ECX4WP3SV/graph.json","fetch_events":"https://pith.science/api/pith-number/TI7PGOHMNSC25UJM3ECX4WP3SV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/action/storage_attestation","attest_author":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/action/author_attestation","sign_citation":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/action/citation_signature","submit_replication":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/action/replication_record"}},"created_at":"2026-07-05T00:33:40.678857+00:00","updated_at":"2026-07-05T00:33:40.678857+00:00"}